MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data
arXiv:2106.09643
Abstract
Class-imbalanced data, in which some classes contain far more samples than others, is ubiquitous in real-world applications. Standard techniques for handling class-imbalance usually work by training on a re-weighted loss or on re-balanced data. Unfortunately, training overparameterized neural networks on such objectives causes rapid memorization of minority class data. To avoid this trap, we harness meta-learning, which uses both an ''outer-loop'' and an ''inner-loop'' loss, each of which may be balanced using different strategies. We evaluate our method, MetaBalance, on image classification, credit-card fraud detection, loan default prediction, and facial recognition tasks with severely imbalanced data, and we find that MetaBalance outperforms a wide array of popular re-sampling strategies.
References in corpus (6)
- SMOTE: Synthetic Minority Over-sampling Technique
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- mixup: Beyond Empirical Risk Minimization
- Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation
- Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks
- Removing Class Imbalance using Polarity-GAN: An Uncertainty Sampling Approach